Quality control and filtering results from cellranger

Sample info and environment setup

PRJNA723584

setwd("/media/jacopo/Elements/re_align/MM/PRJNA723584/SAMN18822747/SRR14295364/")
# Load the libraries (from Sarah script + biomart)
library(tidyverse) # packages for data wrangling, visualization etc
library(Seurat) # scRNA-Seq analysis package
library(clustree) # plot of clustering tree 
library(ggsignif) # Enrich your 'ggplots' with group-wise comparisons
library(clusterProfiler) #The package implements methods to analyze and visualize functional profiles of gene and gene clusters.
library(org.Hs.eg.db) # Human annotation package neede for clusterProfiler
library(ggrepel) # extra geoms for ggplo2
library(patchwork) #multiplots
library(reticulate)

Load and process cellranger data

Load and do the QC for the cellranger data

#list.files(".")
dat <- Read10X(data.dir ="./out/counts_filtered/")
dat <- CreateSeuratObject(dat) # Create the seurat object from the 10x data
kb.initial <- dat@assays[["RNA"]]@counts@Dim[[2]]
cat("Initial number of cells:", kb.initial, 
    "\nNumber of genes:",  dat@assays[["RNA"]]@counts@Dim[[1]])
## Initial number of cells: 17512 
## Number of genes: 36601

Quality Control

Empty cells were already filtered, check for % mt RNA and death markers:

# first calculate the mitochondrial percentage for each cell
dat$percent_mt <- PercentageFeatureSet(dat, pattern="^MT.")
# make violin plots
mt_rna = 20
max_counts = 40000



# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
VlnPlot(dat, features = c("nCount_RNA", "nFeature_RNA", "percent_mt"))  + geom_hline(yintercept=mt_rna, linetype = "dotted")

plot1 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "percent_mt")
plot1 <- plot1 + geom_hline(yintercept=mt_rna, linetype = "dotted")
plot2 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "nFeature_RNA")
plot2 <- plot2 + geom_vline(xintercept = max_counts, linetype = "dotted")
plot1 

plot2

##  cells retained by mt RNA content ( 20 %): 11690 
##  percentage of retained cells: 66.75 %
## cells retained by counts ( 40000 ): 11660 
##  percentage of retained cells: 66.58 %

Check the distribution of the cells with low counts and control death markers:

min_counts = 300


hist(dat@meta.data$nCount_RNA, breaks = 100, xlab = "Counts")

hist(dat@meta.data$nCount_RNA, breaks = 1000, xlab = "Counts", xlim = c(0,5000))

hist(dat@meta.data$nCount_RNA, breaks = 10000, xlab = "Counts", xlim = c(0,1000))
abline(v=min_counts, col="red", lty = 3)

The evident peak of cells with < 200 counts could contain dying cells.

# Subset the dataset to focus only on those cells with low counts
dat.lowcount <- subset(dat, subset = nCount_RNA < min_counts)

# Get the mean of the counts for each gene and sort them decreasing
meanCounts <- rowMeans(GetAssayData(object = dat.lowcount, slot = 'counts'))
meanCounts <- sort(meanCounts, decreasing = T)

# A boxplot can help to observe the distribution of the means
#boxplot(meanCounts)

# Print the most highly expressed genes
head(meanCounts, 30)
##       IGKC      RPLP1      IGHA1      RPL10      RPS28     JCHAIN     EEF1A1 
## 18.1895457  2.3978994  2.1729360  1.6587689  1.3561309  1.2667318  1.2318026 
##     MALAT1      RPS18        B2M      RPL41       SSR4      RPS14      RPL32 
##  1.1812408  0.8873962  0.8092330  0.7486566  0.7188569  0.7010259  0.6871031 
##      RPS4X     TMSB4X      RPS27       RPL3     MT-CO2      RPS19      RPL30 
##  0.6331216  0.6311676  0.6211529  0.6008793  0.5862237  0.5857352  0.5708354 
##      RPL29     RPL18A      RPL19     RPS27A      RPS23     MT-CO3      RPL39 
##  0.5703468  0.5657059  0.5212506  0.4868100  0.4777723  0.4670249  0.4658036 
##       RPL8      RPL18 
##  0.4572545  0.4494382
## cells retained by counts ( 300 ): 7565 
##  percentage of retained cells: 43.2 %

dir.create("result")
saveRDS(dat, file = "./result/SAMN18822747_clean_QC.Rds")

Feature selection

#Normalize
dat <- NormalizeData(dat)
# Find the first 4000 variabe features
dat <- FindVariableFeatures(dat, selection.method = "vst", nfeatures = 4000)

Data scaling

Set mean expression to 0 and variance across 1 to avoid highly expressed genes drive the forwarding analyses. Since negative expression is meaningless, scaled data are useful only for UMAP and clustering

# scale data, the scaled data are saved in:
# dat[["RNA"]]@scale.data

all.genes <- rownames(dat)

dat <- ScaleData(dat, vars.to.regress = c("percent_mt","nCount_RNA"))

Dimensionality reduction

dat <- RunPCA(dat, features = VariableFeatures(object = dat), verbose = F, seed.use = 1)
print(dat[["pca"]], dims = 1:5, nfeatures = 5)
## PC_ 1 
## Positive:  MKI67, NUSAP1, CENPF, TOP2A, ASPM 
## Negative:  RPL10, RPL19, RPS14, RPL41, RPL32 
## PC_ 2 
## Positive:  IGHA1, IGHV3-43, IFI6, LINC01725, PDK1 
## Negative:  MKI67, NUSAP1, CENPF, TOP2A, ASPM 
## PC_ 3 
## Positive:  RPLP1, RPS18, IGHA1, RPS4X, RPS5 
## Negative:  TMSB4X, NEAT1, KLF2, CCPG1, HLA-B 
## PC_ 4 
## Positive:  NEAT1, ZFP36L2, PCDH9, FCRL5, AHNAK 
## Negative:  PPIB, MYDGF, SEC11C, PRDX4, MANF 
## PC_ 5 
## Positive:  S100A10, RASGRP2, CLIC1, TSPO, KLF2 
## Negative:  MZB1, PDK1, HDLBP, SEL1L, NME1

UMAP

UMAP is a graph-based method of clustering. The first step in this process is to construct a KNN graph based on the euclidean distance in PCA space:

dat <- FindNeighbors(dat, dims = 1:20)

The graph now can be used as input for the function runUMAP()

dat <- RunUMAP(dat, dims = 1:20, seed.use = 1)
DimPlot(dat, reduction = 'umap', seed = 1)

Final plots:

## QC metrics

## markers